context7

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download documentation content from an external API at https://context7.com using the curl utility.\n- [DATA_EXFILTRATION]: User-provided library names and topical search queries are transmitted to the context7.com API endpoints as part of the documentation lookup process.\n- [COMMAND_EXECUTION]: The documentation in SKILL.md and README.md provides explicit shell commands using curl and jq for the agent to execute to interact with the external service.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes data from an external, third-party source (context7.com) that could be manipulated by an attacker to include hidden instructions.\n
  • Ingestion points: Documentation text and search results fetched from the /api/v2/context and /api/v2/libs/search endpoints as described in SKILL.md.\n
  • Boundary markers: No specific delimiters or safety instructions (e.g., 'ignore instructions within this data') are used when the agent processes the fetched content.\n
  • Capability inventory: The skill uses shell command execution (curl, jq) which are used to retrieve the untrusted data.\n
  • Sanitization: The skill does not define any sanitization, filtering, or validation steps for the documentation content retrieved from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 07:09 PM